# io.github.mrhpython/lens-mcp (npm · @soulfield/lens-mcp)

Outside-in validation gate for AI-generated text; a separate model checks LLM output, fail-closed.

- Trust score: 81/100 (high trust)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-23

## Components

- npm · `@soulfield/lens-mcp`: 81/100 (this document), [markdown](https://verifymcp.io/servers/mrhpython-lens-mcp/soulfield-lens-mcp.md), [page](https://verifymcp.io/servers/mrhpython-lens-mcp/soulfield-lens-mcp)

## Channel facts

- Registry: `npm`
- Package: `@soulfield/lens-mcp`
- Version: `1.1.1`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-09-23.

- **Supply Chain Security**: 98/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - 31 of 95 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 26 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 69/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 1771 tokens (~196/item across 9 items; 9 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 90/100
  - Stability observed for 27 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 9 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 9 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the io.github.mrhpython/lens-mcp server?

io.github.mrhpython/lens-mcp runs locally as an npm package, launched with npx -y @soulfield/lens-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add mrhpython-lens-mcp -- npx -y @soulfield/lens-mcp
```

### Cursor

```json
{
  "mcpServers": {
    "mrhpython-lens-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@soulfield/lens-mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "mrhpython-lens-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@soulfield/lens-mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add mrhpython-lens-mcp -- npx -y @soulfield/lens-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "mrhpython-lens-mcp": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@soulfield/lens-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add mrhpython-lens-mcp --command npx --arg -y --arg @soulfield/lens-mcp
```

### Hermes

```yaml
mcp_servers:
  mrhpython-lens-mcp:
    command: "npx"
    args: ["-y", "@soulfield/lens-mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "mrhpython-lens-mcp": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "@soulfield/lens-mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add mrhpython-lens-mcp -t stdio -c npx -a -y @soulfield/lens-mcp
```

### Other

```json
{
  "mcpServers": {
    "mrhpython-lens-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@soulfield/lens-mcp"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-09-22 (score 81, +1)

No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-19 (score 80, +1)

No change was recorded against any check on this day. Stability & Change Management went from 73 to 77. That category is still filling its 30-day observation window: 22 days of observed history at the previous scan, 23 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-17 (score 79, +1)

No change was recorded against any check on this day. Stability & Change Management went from 67 to 70. That category is still filling its 30-day observation window: 20 days of observed history at the previous scan, 21 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-15 (score 78, +1)

No change was recorded against any check on this day. Stability & Change Management went from 60 to 63. That category is still filling its 30-day observation window: 18 days of observed history at the previous scan, 19 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-13 (score 77, +1)

No change was recorded against any check on this day. Stability & Change Management went from 53 to 57. That category is still filling its 30-day observation window: 16 days of observed history at the previous scan, 17 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-11 (score 76, +1)

No change was recorded against any check on this day. Stability & Change Management went from 47 to 50. That category is still filling its 30-day observation window: 14 days of observed history at the previous scan, 15 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-09 (score 75, +1)

No change was recorded against any check on this day. Stability & Change Management went from 40 to 43. That category is still filling its 30-day observation window: 12 days of observed history at the previous scan, 13 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-07 (score 74, +1)

No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

## MCP tools (9)

### `validate_content` (~276 tokens)

Validate Content

Run the 10-lens validation gate on AI-generated content. Returns pass/fail, per-lens results, violation details, and a deterministic 0-10 score derived from violation counts (10 = clean, floors at 0; computed by the API tier layer, not by the LLM — the LLM-emitted 0-100 score was removed 2026-07-30). Requires SOULFIELD_API_KEY. Supports domains: general, finance, marketing, legal, seo, agency. WIRE CONTRACT (since 2026-08-10): each lens carries status (ran|skipped|error) and passed is null whenever no verdict was produced — parse passed===false as the violation signal, never !passed. HALT SEMANTICS: Rights runs first and halts the run on a critical violation; in a halted response downstream judged lenses read passed:null/status:skipped (unknown, not clean — consciousScan is non-blocking and keeps passed:true, its status:skipped is the never-ran signal).

Input parameters:

- `context` (string): Audience/purpose context for Relevance lens (Lens 9). Omit to skip Relevance silently.
- `domain` (string): Domain context for validation (default: general)
- `text` (string, required): The AI-generated content to validate

### `scrub_pii` (~193 tokens)

Scrub PII

Scan text for structured PII and secrets (emails, UK/US phone numbers, credit-card numbers, US SSNs, UK NI/UTR numbers, database connection strings, and common API-key/credential patterns) via the hosted Lens API. Returns scrubbed text with each match replaced by a generic [REDACTED] marker (the finding TYPE — email, phone_uk, ni_number, etc. — appears only in the findings list, not in the replacement), plus that findings list. It scrubs structured identifiers only: personal NAMES survive, so scrubbed output is not anonymized. Pattern-based server-side scan, no LLM call. Targets structured identifiers — it does not detect personal names or free-form PII, and coverage of structured formats is best-effort, not exhaustive. Requires SOULFIELD_API_KEY.

Input parameters:

- `text` (string, required): The text to scan for PII

### `lens_health` (~30 tokens)

Lens API Health Check

Check if the Soulfield Lens API service is running and responsive. Returns status and version. No auth required.

### `lens_catches_relevant` (~238 tokens)

Prior Catches (institutional defect memory)

Read the defect bank BEFORE validating: prior named defects for an artifact type, most-recurrent patterns first. This is the institutional memory that makes the gate improve over time — the recurring traps tell you where this class of artifact has failed before. Any pattern at threshold is marked [PROMOTE], meaning it recurs often enough to deserve a deterministic check. Runs the local lens-kit CLI, no LLM call. Omit artifact_type and pass all=true when the type has no history yet.

Input parameters:

- `all` (boolean): Surface every catch regardless of artifact type
- `artifact_type` (string): Artifact type to filter by, e.g. landing-copy, research-brief, content-pack
- `cwd` (string): Working directory to run in. catches.jsonl is read from and written to here. Defaults to the server's cwd.
- `domain` (string): Also filter by domain, e.g. marketing, finance, agency
- `format` (string): block = paste-ready surface (default); json = raw records
- `threshold` (integer): Recurrence threshold for [PROMOTE] lines (default 3)

### `lens_catches_add` (~235 tokens)

Record a Catch (append to defect memory)

Append a NAMED DEFECT to the defect bank so it is caught next time. Record what was WRONG, the general pattern it is an instance of, and the forward rule that prevents it — doctrine REJECTS routine passes, so only log actual defects. Set self_catch=true when the defect was a failure of your own validation discipline. This is the write half of the improvement loop: enough recurrences of a pattern promote it to a deterministic check.

Input parameters:

- `artifact_type` (string, required): Artifact type, e.g. landing-copy, research-brief
- `catch` (string, required): What was WRONG (the specific defect found)
- `cwd` (string): Working directory to run in. catches.jsonl is read from and written to here. Defaults to the server's cwd.
- `domain` (string, required): Domain, e.g. marketing, finance, agency
- `pattern` (string, required): The general trap this is an instance of
- `rule` (string, required): The forward rule that prevents this next time
- `self_catch` (boolean): True if this was a failure of the validator's own discipline

### `lens_catches_stats` (~93 tokens)

Catch Recurrence Stats

Per-pattern recurrence counts across the defect bank. Any pattern at or above the threshold gets a PROMOTE-to-deterministic-check suggestion — that is the signal a recurring judgment call should become a cheap fixed check instead. Use this to decide what to harden next.

Input parameters:

- `cwd` (string): Working directory to run in. catches.jsonl is read from and written to here. Defaults to the server's cwd.

### `lens_consistency_leaks` (~289 tokens)

Forbidden-String Leak Scan

Scan customer-facing files for deny-list terms (CASE-INSENSITIVE literal match — note lens_consistency_markers is case-SENSITIVE, they differ). Deterministic, no LLM. Exit 6 on a hit. Run this on EVERY customer-facing file before any irreversible publish: it is the check that catches a real client name, an internal codename or a banned absolute surviving into shipped copy. A credential scanner will not find these, because nothing here is a credential. IMPORTANT — a hit proves the STRING IS PRESENT, which is authoritative; it does not by itself prove a violation, because the match is NEGATION-BLIND: a banned phrase quoted in order to disclaim it ('we will not give you a guaranteed accuracy number') looks identical to the same phrase asserted. Adjudicate before acting. Deny terms should therefore be strings that are wrong in EVERY context (a real client name, an internal codename), not claims-you-do-not-make — those belong in a lens prompt.

Input parameters:

- `cwd` (string): Working directory to run in. catches.jsonl is read from and written to here. Defaults to the server's cwd.
- `deny` (array): Extra deny terms, added to the profile's consistency.deny
- `files` (array, required): Local file path(s) to scan
- `profile` (string): Profile YAML providing consistency.deny

### `lens_consistency_numbers` (~156 tokens)

Number Parity (summary vs body)

Check that every numeric literal in a summary actually appears in the body it summarizes. Deterministic, no LLM, exit 6 on a violation. Catches the invented figure — the number a summary asserts that its source never stated. TRIPWIRE, not an oracle: literal matching only, no semantic or derived arithmetic, so a legitimately computed total will flag. Review a hit, do not auto-trust it.

Input parameters:

- `body` (string, required): The body file the summary summarizes
- `cwd` (string): Working directory to run in. catches.jsonl is read from and written to here. Defaults to the server's cwd.
- `summary` (string, required): The summary file (its numbers must appear in the body)

### `lens_consistency_markers` (~261 tokens)

Marker Parity (source vs rendered)

Check that evidence markers counted in a source artifact survive into every rendered output. Deterministic, no LLM, exit 6 on a violation. Catches the caveat, citation or hedge that gets dropped between formats — the source says 'as-of 2026-04' and the rendered deck quietly does not. Matching is CASE-SENSITIVE (unlike lens_consistency_leaks, which is case-insensitive), so pick markers whose casing is stable across source and render: 'TRIPWIRE' in the source will NOT match 'Tripwire' in the render and will read as dropped when nothing was. TRIPWIRE: a deliberate subset render also under-counts legitimately. Before treating a hit as a removed caveat, grep the rendered file case-insensitively.

Input parameters:

- `cwd` (string): Working directory to run in. catches.jsonl is read from and written to here. Defaults to the server's cwd.
- `markers` (array): Explicit marker strings (otherwise taken from the profile)
- `profile` (string): Profile YAML providing the marker set
- `rendered` (array, required): Rendered output file(s) to check against the source
- `source` (string, required): The source artifact (authoritative marker counts)

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/mrhpython-lens-mcp/soulfield-lens-mcp#diagnostics

## Score history

- 2026-09-23: 81
- 2026-09-22: 81
- 2026-09-21: 80
- 2026-09-20: 80
- 2026-09-19: 80
- 2026-09-18: 79
- 2026-09-17: 79
- 2026-09-16: 78
- 2026-09-15: 78
- 2026-09-14: 77
- 2026-09-13: 77
- 2026-09-12: 76
- 2026-09-11: 76
- 2026-09-10: 75
- 2026-09-09: 75
- 2026-09-08: 74
- 2026-09-07: 74
- 2026-09-06: 73
- 2026-09-05: 73
- 2026-09-04: 73
- 2026-09-03: 69
- 2026-09-02: 69
- 2026-09-01: 69
- 2026-08-31: 69
- 2026-08-30: 69
- 2026-08-29: 69
- 2026-08-28: 69
- 2026-08-27: 54

## Common questions

### What is the io.github.mrhpython/lens-mcp server?

io.github.mrhpython/lens-mcp is listed in the public MCP registry as io.github.mrhpython/lens-mcp. Outside-in validation gate for AI-generated text; a separate model checks LLM output, fail-closed. This page covers its npm package (@soulfield/lens-mcp).

### Is the io.github.mrhpython/lens-mcp server safe to use?

io.github.mrhpython/lens-mcp scores 81 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 23 September 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the io.github.mrhpython/lens-mcp server expose?

io.github.mrhpython/lens-mcp exposes 9 tools: validate_content, scrub_pii, lens_health, lens_catches_relevant, lens_catches_add, and 4 more. Their descriptions and schemas cost roughly 1,771 tokens of context every time the server is loaded.

### Is the io.github.mrhpython/lens-mcp server still maintained?

io.github.mrhpython/lens-mcp is still listed as active in the MCP registry. We last reached this channel on 23 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the io.github.mrhpython/lens-mcp server under?

io.github.mrhpython/lens-mcp declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- npm package: https://www.npmjs.com/package/@soulfield/lens-mcp
- Socket report: https://socket.dev/npm/package/@soulfield/lens-mcp
- Repository: https://github.com/mrhpython/lens-mcp
- Changelog RSS feed: https://verifymcp.io/servers/mrhpython-lens-mcp/soulfield-lens-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/mrhpython-lens-mcp/soulfield-lens-mcp.json
- HTML version of this page: https://verifymcp.io/servers/mrhpython-lens-mcp/soulfield-lens-mcp